181–190 of 346 posts
Why I left that idea is because as a developer I know that was needed but I have limited time so I need to build that is really next path forward.
I am working on whole dev space that can run on my Mac M4 or similar specs. I needed to revamp everything (LLM thinking) from ground up even models. My idea is mixing deterministic nature of existing tooling (non-LLM tooling) with non-deterministic nature of LLMs.
Earlier quoted context omitted.
Tell me more about the ideas behind Cordis the plugin system. The paper is a bit too mathy to consume and I think it deserves a more accessible post or something.
You're making demands (like you would to an llm) instead of asking questions (like you would to a human). The GP didn't even offer to answer questions
Earlier quoted context omitted.
Yeah. LLMs have their place and they are definitely super human at short length tasks, but I feel like a large part of the "AI boom" is trying to get the computer to do something in a worse way then it already could.
But that "worse way" makes AI labs and investors a lot of money... If the perception that "worse" is accompanied with needing less human intervention, i.e. less labor, worse is better from a business perspective...
Hi I'm one of the authors of DeepSeek Harness. It's just an early developer preview version we're presenting in MIT license currently. Expect lots of rough edges and compatibility-breaking changes. Any feedback and suggestions are more than welcome!
Earlier quoted context omitted.
New coding harness that seems to have some novel concepts and one of the pretty cool things on their landing page for it here: https://deepseek.com/harness/en/ is the Every Run is Traceable view: "Everything the model sees is recorded in an append-only session log: system prompts, reasoning, tool calls and results, subagent scheduling, and every context injection. In the Trajectory view, you can inspect these records…
I promise this isn't meant to be snarky, but is that not just...logs?
Tangential but, are there benchmarks out there on how languages affect latent spaces and performance of these models? This other day I was looking at that “caveman” skill, and was shocked to see it evolved to become a company, and, in one of its modes, the highest form of compression seems to be “Wenyan” which is Classical Chinese. Should I get started on learning Chinese?
Earlier quoted context omitted.
1. it's built for async 2. runs everywhere 3. interpreted, making it fast to iterate on 4. decent performance 5. most popular language, llms are decent at writing it
JVM has real and virtual threads and arguably just as good if not better on all these points. (I actually have/am writing a harness in Java fwiw, but mostly as a hobby/experimentation)
Hi I'm one of the authors of DeepSeek Harness. It's just an early developer preview version we're presenting in MIT license currently. Expect lots of rough edges and compatibility-breaking changes. Any feedback and suggestions are more than welcome!
Earlier quoted context omitted.
Also isn't OpenAI's Codex written in Rust?
I don’t think so it’s an npm package iirc
Is there any place to see benchmarks for harnesses (not models)? I'd love to see these things compared.